Method and device for generating painting display sequence, and computer storage medium

Abstract

A method and device for generating a painting display sequence, and a computer storage medium are provided. The method for generating a painting display sequence comprises the following steps: acquiring painting data of a region of interest (ROI); clustering the painting data in a predetermined group and obtaining clustering results; and generating the painting display sequence according to the clustering result.

1 . A method for generating a painting display sequence, comprising the steps of:
 acquiring painting data and user behavior data;   clustering the painting data in a predetermined group to obtain a clustering result; and   generating a painting display sequence according to the clustering result.   
     
     
         2 . The method of  claim 1 , wherein the predetermined group comprises multiple clustering algorithms that use different principles and a fusion clustering algorithm that fuses the clustering result. 
     
     
         3 . The method of  claim 2 , wherein clustering the painting data further comprises
 processing the painting data, and obtaining feature vectors with reduced dimension;   inputting the feature vectors into each of the multiple clustering algorithms, and obtaining intermediate clustering results that characterize incidence relation between paintings; and   inputting the intermediate clustering results into the fusion clustering algorithm, and obtaining the clustering result.   
     
     
         4 . The method of  claim 2 , wherein the multiple clustering algorithms that use different principles comprise at least two of:
 clustering algorithm based on classifying, clustering algorithm based on level, clustering algorithm based on density, and clustering algorithm based on model.   
     
     
         5 . The method of  claim 3 , wherein processing the painting data further comprises:
 extracting feature vectors based on article according to the painting data and the user behavior data;   fusing the feature vectors, and obtaining a fusion feature vector; and   converting, by using a principal component analysis, the fusion feature vector into a feature vector with reduced dimension.   
     
     
         6 . The method of  claim 5 , wherein extracting the feature vectors further comprises:
 extracting, on a layer-by-layer basis and by using a stacked auto-encoder, features from painting image information of the painting data, reducing dimension of the extracted features, and obtaining a high-order feature vector corresponding to the painting data;   encoding, by using one-hot encoder, a category feature from painting category information of the painting data, normalizing the category feature, and obtaining a first painting feature vector;   decomposing, by using alternating least squares, structured behavior data from user behavior data, and obtaining a second painting feature vector; and   extracting, by using latent dirichlet allocation, a latent topic probability vector from unstructured behavior data of the user behavior data; and   wherein the high-order feature vector, the first painting feature vector, the second painting feature vector and the latent topic probability vector are feature vectors based on article.   
     
     
         7 . The method of  claim 3 , wherein inputting the intermediate clustering results further comprises:
 establishing an incidence matrix between two paintings in a painting set, wherein initial value of each element in the incidence matrix is 0;   sequentially scanning each of the intermediate clustering results by using the fusion clustering algorithm;   adjusting the value of corresponding elements in an incidence matrix of two paintings, when an intermediate clustering result classifies the two paintings into a same class cluster; and   classifying two paintings into a same class cluster when scanning has been completed and value of elements in an incidence matrix are greater than a predetermined element value threshold, and obtaining a final clustering result.   
     
     
         8 . The method of  claim 7 , wherein adjusting the value of corresponding elements further comprises:
 increasing the value of corresponding elements in an incidence matrix of two paintings by 1, when an intermediate clustering result classifies the two paintings into a same class cluster.   
     
     
         9 . The method of  claim 1 , wherein the painting data comprise painting image information and painting feature information, and the painting feature information comprises at least one of the following: category, topic, size, author, year, and material. 
     
     
         10 . A device for generating a painting list, comprising:
 a memory; and   one or more processors, wherein the memory and the one or more processors are connected with each other; and   the memory stores computer-executable instructions for controlling the one or more processors to:   acquire, by an inputting layer, painting data and user behavior data;   cluster, by a clustering layer, the painting data in a predetermined group to obtain a clustering result; and   generate, by an outputting layer, the painting display sequence according to the clustering result.   
     
     
         11 . The device of  claim 10 , wherein the predetermined group comprises multiple clustering algorithms that use different principles and a fusion clustering algorithm that fuses the clustering result. 
     
     
         12 . The device of  claim 11 , wherein the clustering layer further comprises:
 a feature vector acquiring module that processes the painting data, and obtains feature vectors with reduced dimension;   an intermediate clustering result acquiring module that inputs the feature vectors into each of the multiple clustering algorithms, and obtains intermediate clustering results that characterize incidence relation between paintings; and   a fusion clustering result acquiring module that inputs the intermediate clustering results into the fusion clustering algorithm, and obtains a final clustering result.   
     
     
         13 . The device of  claim 11 , wherein the feature vector acquiring module further comprises:
 an article feature vector extracting unit that extracts feature vectors based on article, according to the painting data and user behavior data;   a fusion feature vector acquiring unit that fuses the feature vectors and obtains a fusion feature vector; and   a feature vector converting unit that converts, by using a principal component analysis, the fusion feature vector into a feature vector with reduced dimension.   
     
     
         14 . The device of  claim 13 , wherein the article feature vector extracting unit further comprises:
 a high-order feature vector acquiring sub-unit that extracts, on a layer-by-layer basis and by using a stacked auto-encoder, features from painting image information of the painting data, reduces dimension of the extracted features, and obtains a high-order feature vector corresponding to the painting data;   a first painting vector acquiring sub-unit that encodes, by using one-hot encoder, a category feature from painting category information of the, normalizes the category feature, and obtains a first painting feature vector;   a second painting vector acquiring sub-unit that decomposes, by using alternating least squares, structured behavior data and obtaining a second painting feature vector; and   a latent topic probability vector acquiring sub-unit that extracts, by using latent dirichlet allocation, a latent topic probability vector from unstructured behavior data of the user behavior data;   wherein the high-order feature vector, the first painting feature vector, the second painting feature vector and the latent topic probability vector are feature vectors based on article.   
     
     
         15 . The device of  claim 12 , wherein the fusion clustering result acquiring module further comprises:
 an incidence matrix establishing unit that establishes an incidence matrix between two paintings in a painting set, wherein initial value of each element in the incidence matrix is 0;   an intermediate clustering result scanning unit that sequentially scans each of the multiple intermediate clustering results by using the fusion clustering algorithm;   an incidence matrix element value adjusting unit that adjusts value of corresponding elements in a predetermined incidence matrix of two paintings when an intermediate clustering result classifies the two paintings into a same class cluster; and   a painting classifying unit that classifies two paintings into a same class cluster when scanning has been completed and value of element in an incidence matrix are greater than a predetermined element value threshold and obtaining a final clustering result.   
     
     
         16 . A non-transitory computer storage medium comprising computer executable instructions that when executed by one or more processors, cause the one or more processors to perform:
 acquiring painting data and user behavior data;   clustering the painting data in a predetermined group to obtain a clustering result; and   generating a painting display sequence according to the clustering result.   
     
     
         17 . The non-transitory computer storage medium of  claim 16 , wherein the predetermined group comprises multiple clustering algorithms that use different principles and a fusion clustering algorithm that fuses the clustering result. 
     
     
         18 . The non-transitory computer storage medium of  claim 17 , wherein the instructions that cause the one or more processors to perform clustering the painting data further cause the one or more processors to perform:
 processing the painting data, and obtaining feature vectors with reduced dimension;   inputting the feature vectors into each of the multiple clustering algorithms, and obtaining intermediate clustering results that characterize incidence relation between paintings; and   inputting the intermediate clustering results into the fusion clustering algorithm, and obtaining the clustering result.   
     
     
         19 . The non-transitory computer storage medium of  claim 18 , wherein the instructions that cause the one or more processors to perform processing the painting data further cause the one or more processors to perform:
 extracting feature vectors based on article, according to the painting data and the user behavior data;   fusing the feature vectors, and obtaining a fusion feature vector; and   converting, by using a principal component analysis, the fusion feature vector into a feature vector with reduced dimension.   
     
     
         20 . The computer storage medium of  claim 19 , wherein the instructions that cause the one or more processors to perform extracting the feature vectors further cause the one or more processors to perform:
 extracting, on a layer-by-layer basis and by using a stacked auto-encoder, features from painting image information of the painting data, reducing dimension of the extracted features, and obtaining a high-order feature vector corresponding to the painting data;   encoding, by using one-hot encoder, a category feature from painting category information of the painting data, normalizing the category feature, and obtaining a first painting feature vector;   decomposing, by using alternating least squares, structured behavior data from the user behavior data, and obtaining a second painting feature vector; and   extracting, by using latent dirichlet allocation, a latent topic probability vector from unstructured behavior data of the user behavior data; and   wherein the high-order feature vector, the first painting feature vector, the second painting feature vector and the latent topic probability vector are feature vectors based on article.   
     
     
         21 . (canceled)